Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     facilitates
    -0.06
    utt
    -0.06
     shore
    -0.06
    _caption
    -0.06
    .end
    -0.06
    session
    -0.06
     사라
    -0.06
    เส
    -0.06
    その他
    -0.06
     تاب
    -0.06
    POSITIVE LOGITS
    eği
    0.07
    
    0.06
    _az
    0.06
    	of
    0.06
     �
    0.06
    床
    0.06
    iloc
    0.06
    ディ
    0.06
     trif
    0.06
    (INPUT
    0.06
    Act Density 0.003%

    No Known Activations